MixTEA：基于混合教学的半监督实体对齐
MixTEA: Semi-supervised Entity Alignment with Mixture Teaching
AI总结：
针对半监督实体对齐中伪映射噪声大、不确定性被忽略的问题，提出MixTEA方法，通过双向投票估计不确定性、匹配多样性校正降低噪声影响，结合混合教学指导模型学习，在基准数据集上取得更优效果。
摘要：
半监督实体对齐（EA）是一项兼具实用性与挑战性的任务，其难点在于缺乏足够的标注映射作为训练数据。现有研究大多通过为无标注实体生成伪映射来解决这一问题，但这类方法要么受错误（噪声）伪映射的干扰，要么在很大程度上忽略了伪映射的不确定性。本文提出了一种全新的半监督EA方法，命名为MixTEA，该方法通过手动标注映射与概率伪映射的端到端混合教学来指导模型学习。我们首先使用少量标注映射按标准流程训练一个学生模型。更关键的是，在伪映射学习阶段，我们提出了双向投票（BDV）策略，该策略融合不同方向的对齐决策，通过联合匹配置信度分数来估计不确定性。同时，我们还设计了基于匹配多样性的校正（MDR）模块来调整伪映射学习，从而降低噪声映射带来的负面影响。在基准数据集上的大量实验结果以及进一步分析均证明了本文所提方法的优越性与有效性。
英文摘要：
Semi-supervised entity alignment (EA) is a practical and challenging task because of the lack of adequate labeled mappings as training data. Most works address this problem by generating pseudo mappings for unlabeled entities. However, they either suffer from the erroneous (noisy) pseudo mappings or largely ignore the uncertainty of pseudo mappings. In this paper, we propose a novel semi-supervised EA method, termed as MixTEA, which guides the model learning with an end-to-end mixture teaching of manually labeled mappings and probabilistic pseudo mappings. We firstly train a student model using few labeled mappings as standard. More importantly, in pseudo mapping learning, we propose a bi-directional voting (BDV) strategy that fuses the alignment decisions in different directions to estimate the uncertainty via the joint matching confidence score. Meanwhile, we also design a matching diversity-based rectification (MDR) module to adjust the pseudo mapping learning, thus reducing the negative influence of noisy mappings. Extensive results on benchmark datasets as well as further analyses demonstrate the superiority and the effectiveness of our proposed method.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
